Speech & Text | Blog from AssemblyAI

Abstract green cone illustration

Why streaming transcription drifts to English on multilingual audio — and how to fix language steering

By

Kelsey Foster

,

Growth

Abstract green mobius illustration

AssemblyAI vs Deepgram for voice agents

By

Kelsey Foster

,

Growth

Abstract green mobius illustration

Speech-to-speech voice agents: how the architecture works

By

Kelsey Foster

,

Growth

Abstract green half-sphere illustration

Best platforms for enterprise voice agents

By

Kelsey Foster

,

Growth

Abstract green cone illustration

How accurate are AI transcripts for technical or medical terms?

By

Kelsey Foster

,

Growth

Abstract green cylinder illustration

Transcription accuracy vs. transcription quality: why the gap matters

By

Kelsey Foster

,

Growth

Abstract green mobius illustration

How to build with the Voice Agent API

By

Kelsey Foster

,

Growth

Abstract green cylinder illustration

How I built a voice agent without writing (or understanding) any code

By

Devon Malloy

,

Staff Growth Manager

Abstract green cylinder illustration

Why AssemblyAI's Voice Agent API is designed for coding agents

By

Devon Malloy

,

Staff Growth Manager

Abstract green cylinder illustration

The production ceiling: where voice agent stacks start showing their limits

By

Ryan Seams

,

VP, Customer Solutions

Abstract green mobius illustration

The voice agent accuracy problem nobody benchmarks

By

Devon Malloy

,

Staff Growth Manager

Abstract green cylinder illustration

How the Voice Agent API pipeline works, from audio in to audio out

By

Devon Malloy

,

Staff Growth Manager

No results found!

Please try different search parameters.

Featured

Abstract green half-sphere illustration

September 30, 2026

Why your word error rate (WER) benchmark might be lying to you

By

Zackary Klebanoff

,

Applied AI Lead

Abstract green diamond illustration

September 30, 2026

AssemblyAI Universal-3.5 Pro vs OpenAI Whisper (2026)

By

Patrick Loeber

,

Senior Developer Advocate

Abstract blue sphere illustration

September 29, 2026

Universal-3.6 Pro Realtime is live

By

Madison Bernstein

,

Product Marketing

Abstract blue sphere illustration

September 29, 2026

Universal-3.6 Pro Realtime: trained on real conversations, built for real voice agents

By

Ilya Sklyar

,

Research

Releases & updates

Abstract blue sphere illustration

Universal-3.6 Pro Realtime is live

By

Madison Bernstein

,

Product Marketing

Abstract blue sphere illustration

Universal-3.6 Pro Realtime: trained on real conversations, built for real voice agents

By

Ilya Sklyar

,

Research

Cheerful computers passing messages and parcels between green hands

Universal-3.5 Pro is now on OpenRouter

By

David Lange

,

Applied AI Engineer

Abstract blue levels illustration

Introducing our Dictation API

By

Madison Bernstein

,

Product Marketing

Insights & use cases

Abstract green mobius illustration

Ambient scribes beyond healthcare: Building for veterinary and legal

By

Kelsey Foster

,

Growth

Abstract green cone illustration

When keyterm prompting backfires

By

Kelsey Foster

,

Growth

Abstract green sphere illustration

The voice agent launch runbook: ramp, rollback, and on-call

By

Kelsey Foster

,

Growth

Abstract green sphere illustration

How to evaluate a speech-to-text API for an education platform (2026)

By

Kelsey Foster

,

Growth

News

Abstract yellow diamond grid illustration

Building voice agents for the real world: 7 takeaways from our NYC meetup with LiveKit

By

Kelsey Foster

,

Growth

Abstract yellow diamond grid illustration

AssemblyAI Named a Leader in G2’s Spring 2026 Voice Recognition Report

By

Devon Malloy

,

Staff Growth Manager

Abstract yellow triangle grid illustration

Voice AI in 2026: Inside the companies and investments shaping the future of speech

By

Kelsey Foster

,

Growth

Abstract yellow diamond grid illustration

Inside AssemblyAI's NYC voice agents January 2026 meetup: Production insights from the front lines

By

Kelsey Foster

,

Growth

Video

Real-time conversation intelligence: The shift from post-call analysis to live insights

By

Kelsey Foster

,

Growth

The ongoing need for human-in-the-loop in conversation intelligence

By

,

Predicting the future: What top AI founders have to say about innovation in 2025

By

Kelsey Foster

,

Growth

Building with AI in 2025: Top advice from leading founders

By

Kelsey Foster

,

Growth

Newsletter

Abstract orange cone illustration

SF Hackathon + In-App Playground + 99 Language Support | Newsletter

By

Devon Malloy

,

Staff Growth Manager

Abstract orange sphere illustration

Streaming STT Performance Update | Newsletter

By

,

Abstract orange sphere illustration

Enhanced diarization + Dovetail case study + G2 wins | Newsletter

By

,

Abstract orange sphere illustration

Build Powerful Speech AI Apps with AssemblyAI & Speaker Diarization Tutorials

By

Smitha Kolan

,

Developer Educator

Subscribe to AssemblyAI’s newsletter

Thank you for subscribing!

Oops! Something went wrong while submitting the form.

Unlock the value of voice data

Build what’s next on the platform powering thousands of the industry’s leading of Voice AI apps.

Try our API for free Contact sales